get_assistants
AI agents call get_assistants to retrieve information from MCP AI Agent Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information about available assistants. It performs a query operation with no capacity to modify, delete, or execute code. The absence of a description lowers confidence slightly, but the naming convention and sibling tools (change_assistant, clear_session, send_message) confirm this is a read-only operation. Blast radius is minimal—an AI agent listing assistants cannot cause harm.
From the tool's definition Tool name 'get_assistants' indicates a retrieval operation. Description is empty, but the name and context (sibling tools include session management and assistant switching) strongly suggest this lists or fetches available assistants without side effects.
Attacks that exploit this kind of access
get_assistants. It is categorised as a Read tool in the MCP AI Agent Server MCP Server, which means it retrieves data without modifying state.
Register the MCP AI Agent Server MCP server in PolicyLayer and add a rule for get_assistants: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches MCP AI Agent Server. Nothing to install.
get_assistants is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_assistants rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_assistants. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_assistants is provided by the MCP AI Agent Server MCP server (singularitybridge/mcp-ai-agent-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →